lobby6

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

web crawling with VOSON/Uberlink

http://www.cancer.org.au/

http://www.heartfoundation.org.au/

http://www.msaustralia.org.au/

http://www.mndaust.asn.au/

http://strokefoundation.org.au/

http://www.dementia.org.au/

graph plotted with gephi 0.92

knitr::include_graphics("lobby6modularity_yf.png")

purple = dementia green = cancer council blue= stroke nsf black = heart foundation orange = ms australia red = mnd

knitr::include_graphics("strokeHF.png")

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(DT)

## Warning: package 'DT' was built under R version 3.4.3

#library(ggplot2)
library(plotly)

## Loading required package: ggplot2

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

l6<-readxl::read_xlsx("lobby6income.xlsx")

#mortality from abs
#www.abs.gov.au/ausstats/abs@.nsf/Lookup/by%20Subject/3303.0~2016~Main%20Features~Australia's%20leading%20causes%20of%20death,%202016~3
#MND mortablity from mnd website for 2015
#https://www.mndaust.asn.au/Get-informed/What-is-MND/Facts-and-figures.aspx
#cancer prevalence estimated from living people with cancer from 1982
#https://canceraustralia.gov.au/affected-cancer/what-cancer/cancer-australia-statistics
#https://strokefoundation.org.au/about-stroke/facts-and-figures-about-stroke
#stroke prevalence from NSF

#scatter plot relationship
#use geom_point for each column of data
#specify colour
#specify shape

#remove last 3 rows for analysis
#row 8 to 10
 l6m <-l6 
 l6m = l6m %>% filter(
   !row_number()==7:9
 )


gg<-ggplot(l6m,aes(y=revenue2016))+
  geom_point(aes(x=nodes),colour="red",shape="*")+
  geom_point(aes(x=edges),colour="yellow",shape="=")+
  #geom_point(aes(x=pagerank),colour="blue",shape="+")+
  #geom_point(aes(x=prevalence),colour="green",shape="P")+
  #geom_point(aes(x=death),colour="purple",shape="D")
  ggtitle("Network properties versus Revenue")

#click on point in graph for values
ggplotly(gg)

#write function to perform regression
#apply function over vector
#return vector
Fit=glm(revenue2016~nodes,data=l6m)
summary(Fit)

## 
## Call:
## glm(formula = revenue2016 ~ nodes, data = l6m)
## 
## Deviance Residuals: 
##         1          2          3          4          5          6  
## -22057167   58675368  -11541914  -10576766  -17411703    2912181  
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)
## (Intercept)  31122960  182864048   0.170    0.873
## nodes          -26512     556235  -0.048    0.964
## 
## (Dispersion parameter for gaussian family taken to be 1.121512e+15)
## 
##     Null deviance: 4.4886e+15  on 5  degrees of freedom
## Residual deviance: 4.4860e+15  on 4  degrees of freedom
## AIC: 228.52
## 
## Number of Fisher Scoring iterations: 2

Fit=glm(revenue2016~prevalence,data=l6m)
summary(Fit)

## 
## Call:
## glm(formula = revenue2016 ~ prevalence, data = l6m)
## 
## Deviance Residuals: 
##         1          2          3          4          5          6  
## -26805921   54674562     568265   -9094314  -21773001    2430408  
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)
## (Intercept)  2.765e+07  1.765e+07   1.567    0.192
## prevalence  -1.737e+01  3.848e+01  -0.452    0.675
## 
## (Dispersion parameter for gaussian family taken to be 1.067716e+15)
## 
##     Null deviance: 4.4886e+15  on 5  degrees of freedom
## Residual deviance: 4.2709e+15  on 4  degrees of freedom
## AIC: 228.22
## 
## Number of Fisher Scoring iterations: 2

Fit=glm(revenue2016~death,data=l6m)
summary(Fit)

## 
## Call:
## glm(formula = revenue2016 ~ death, data = l6m)
## 
## Deviance Residuals: 
##         1          2          3          4          5          6  
##  -5658047   44759645  -33914438   -6758600    -304660    1876101  
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)
## (Intercept)  5523723   17866115   0.309    0.773
## death           1260       1012   1.245    0.281
## 
## (Dispersion parameter for gaussian family taken to be 8.087299e+14)
## 
##     Null deviance: 4.4886e+15  on 5  degrees of freedom
## Residual deviance: 3.2349e+15  on 4  degrees of freedom
## AIC: 226.55
## 
## Number of Fisher Scoring iterations: 2

#remove outlier
l6m2 = l6m %>% filter(
   !row_number()==2 )
#node
Fit=glm(revenue2016~nodes,data=l6m2)
summary(Fit)

## 
## Call:
## glm(formula = revenue2016 ~ nodes, data = l6m2)
## 
## Deviance Residuals: 
##        1         2         3         4         5  
## -4168931   1684835   2960749    476533   -953186  
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)  
## (Intercept) -83413426   18136070  -4.599   0.0193 *
## nodes          284254      54657   5.201   0.0138 *
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for gaussian family taken to be 1.004011e+13)
## 
##     Null deviance: 3.0167e+14  on 4  degrees of freedom
## Residual deviance: 3.0120e+13  on 3  degrees of freedom
## AIC: 167.32
## 
## Number of Fisher Scoring iterations: 2

#edge
Fit=glm(revenue2016~prevalence,data=l6m2)
summary(Fit)

## 
## Call:
## glm(formula = revenue2016 ~ prevalence, data = l6m2)
## 
## Deviance Residuals: 
##        1         2         3         4         5  
## -6871092  -5066836   1057465  -2412283  13292746  
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7.680e+06  5.783e+06   1.328    0.276
## prevalence  8.370e+00  1.152e+01   0.727    0.520
## 
## (Dispersion parameter for gaussian family taken to be 8.550639e+13)
## 
##     Null deviance: 3.0167e+14  on 4  degrees of freedom
## Residual deviance: 2.5652e+14  on 3  degrees of freedom
## AIC: 178.03
## 
## Number of Fisher Scoring iterations: 2

#death
Fit=glm(revenue2016~death,data=l6m2)
summary(Fit)

## 
## Call:
## glm(formula = revenue2016 ~ death, data = l6m2)
## 
## Deviance Residuals: 
##        1         2         3         4         5  
## -6687676  -5684961   1521399  -1874062  12725300  
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7281372.2  5682566.4   1.281    0.290
## death           299.2      358.4   0.835    0.465
## 
## (Dispersion parameter for gaussian family taken to be 8.160127e+13)
## 
##     Null deviance: 3.0167e+14  on 4  degrees of freedom
## Residual deviance: 2.4480e+14  on 3  degrees of freedom
## AIC: 177.8
## 
## Number of Fisher Scoring iterations: 2

summary(Fit)

## 
## Call:
## glm(formula = revenue2016 ~ death, data = l6m2)
## 
## Deviance Residuals: 
##        1         2         3         4         5  
## -6687676  -5684961   1521399  -1874062  12725300  
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7281372.2  5682566.4   1.281    0.290
## death           299.2      358.4   0.835    0.465
## 
## (Dispersion parameter for gaussian family taken to be 8.160127e+13)
## 
##     Null deviance: 3.0167e+14  on 4  degrees of freedom
## Residual deviance: 2.4480e+14  on 3  degrees of freedom
## AIC: 177.8
## 
## Number of Fisher Scoring iterations: 2

univ<-function (y,x){
  z=glm(y~x)
  return(z)
}
  

  
#use datable
datatable(l6m)

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.